A curated landscape index of open-source projects, protocols, and standards for AI agent identity, naming, trust verification, governance, and security.
Inspired by the ANS (Agent Name Service) ecosystem and Linux Foundation standards efforts.
What this list is not: A catalog of commercial products, academic papers without implementations, internal enterprise governance systems, or platform- specific trust models from Anthropic, OpenAI, or Google. This is a public open-source snapshot — the actual agent trust landscape is larger but less transparent.
How to use this list: Treat inclusion as a discovery signal, not an adoption recommendation or security endorsement. Before using a listed approach, inspect its first-party documentation, current maintenance state, license, threat model, and fit for the project's observed problem.
This project follows the structural conventions of an Awesome list while intentionally covering an emerging ecosystem more broadly than a traditional personal-recommendation shortlist. Entries are alphabetized within categories; inclusion means they passed this repository's criteria, not that the maintainer endorses their security claims.
- Agent Naming & Discovery
- Agent Identity & Cryptographic Identity
- Agent Governance & Policy Enforcement
- Agent Permissions & Authorization
- Trust Registries & Verification
- Agent Reputation & Scoring
- Audit Trails & Observability
- Security & Scanning
- Skills Curation & Trusted Marketplaces
- Standards, Specifications & Foundations
- Agent-to-Agent Protocols
- Attestation & Confidential Computing
- Related Awesome Lists
DNS-like resolution for AI agents. Core protocol with IETF draft backing.
- A2A Agent Cards - JSON metadata at
/.well-known/agent-card.json. Agents self-describe capabilities and authentication requirements. - Agent Name Service - Reference implementation of the ANS protocol. Registry, transparency log, and IETF draft
draft-narajala-ans-00. - ANS Registry - Registration and resolution for the Agent Name Service.
- ANS SDK for Go - Go SDK for the Agent Name Service.
- ANS SDK for Java - Java SDK for the Agent Name Service.
- ANS SDK for Rust - Rust SDK for the Agent Name Service.
- ERC-8004 Registry - On-chain searchable agent identity registry. Agents register as NFTs with queryable capability metadata.
- route-ans - High-performance ANS resolver with semantic versioning and Redis caching.
Cryptographic identity for agents — DIDs, Ed25519, zero-trust frameworks.
- Agent Identity Protocol (AIP) - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with human-in-the-loop.
- agent-auth - Cryptographic identity and delegation for AI agents.
- agentdnai - Verifiable digital identity, scoped permissions, and audit trails for AI agents.
- AGNTCY Identity - Linux Foundation project. Onboard, create, and verify identities for Agents, MCP Servers, and multi-agent systems.
- Alibaba Open Agent Auth - Enterprise framework implementing Agent Operation Authorization protocol with cryptographic identity binding and fine-grained permission verification.
- ASI - Minimal cryptographic identity standard for agent skill ecosystems. Ed25519 + DID:key + JCS bundling.
- HelixID - Open-source identity and authorization layer for AI agents. Issue verifiable credentials, manage decentralized identifiers.
- OrgKernel - Open-source trust layer for AI agents. Cryptographic agent identity (Ed25519), instance-scoped execution tokens, SHA-256 integrity verification.
- Ratify Protocol - Open cryptographic trust protocol for AI agent authorization. Hybrid Ed25519 + ML-DSA-65 (FIPS 204).
- W3C Decentralized Identifiers (DIDs) - The foundation. Globally unique, self-sovereign identifiers controlled by the subject.
- W3C Verifiable Credentials - Cryptographically signed, tamper-evident, machine-verifiable credentials.
Frameworks for governing autonomous agent behavior — policy enforcement, zero-trust, execution sandboxing, approval gates.
- AegisSwarm-Core - Zero-trust security and governance framework for autonomous multi-agent AI networks. Implements CSA Agentic Trust Framework.
- Agent Governance Toolkit - Microsoft's toolkit for AI agent governance. Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering.
- Agentic Trust Framework - Open specification for Zero Trust governance of autonomous AI agents. Five core elements, four maturity levels.
- Agentoes - Enterprise AI trust platform for safe deployment and management of AI agents.
- Clyro - Governance platform that applies policies and controls to AI agent actions before execution.
- cordum - Open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit.
- cullis - Zero-trust governance for autonomous AI agents in regulated organizations. Self-hosted gateway with verified identity.
- DashClaw - Governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, produce audit trails.
- defenseclaw - Cisco's security governance for agentic AI.
- Deterministic Agent Control Protocol - Governance gateway for AI agents. Bounded, auditable, session-aware control with MCP proxy.
- faramesh-core - Governance-as-Code for AI agents. Declarative constraints with deterministic enforcement.
- Hermes Katana - Defense-in-depth security toolkit for LLM agents. Taint tracking, proxy secret guard, policy engine, and red-team benchmark.
- Lelu - Open-source authorization engine for AI agents. Confidence-aware gating, human-in-the-loop, and policy enforcement.
- lunar.dev - Agent-native MCP Gateway for governance and security.
- pattern8 - AI Agent Governance Framework. Constrain how AI agents behave in your project.
pip install pattern8. - Preventra - Governance, trust, and identity for the agentic economy. Public infrastructure.
- superagentX - Policy-driven autonomous AI agents. Unified Control Plane with centralized tools, identity, and governance.
- veldt-kya - KYA (Know Your Agents). Open-source trust, governance, and evidentiary assurance for autonomous systems.
Fine-grained authorization, delegation, and permission systems for agent tool execution.
- ActionWarrant - Local CLI for verifying signed, scoped permission artifacts before agent actions.
- agent-passport - Authorization for AI agents. Scoped permissions, spend limits, delegation chains, instant revocation. Ed25519-signed.
- agentlock - Adversarially benchmarked pre-action agent authorization. Framework-agnostic tool permissions.
- ampersona - Rust platform for AI agent governance: identity (psychology, voice, capabilities) + authority (scoped actions, deny-by-default).
- Emilia Protocol - Offline-verifiable authorization-receipt protocol for controlling irreversible agent actions.
- grantex - Identity, authorization, and audit infrastructure for AI agents.
- Jean-Claw-Van-Damme - Authorization gatekeeper for OpenClaw agents. Scoped grants, time-bound permissions, skill scanning.
- permguard - Authorization engine for today's systems and tomorrow's agentic world.
- permitrail - Open-source permission and audit layer for AI agents that take real actions.
- Pi Permission System - Permission enforcement extension for the Pi coding agent.
- spicebox - Fine-grained permissions for AI coding agents (by AuthZed / SpiceDB).
- theauth - Auth for AI agents and humans. First-class agent identity, MCP, OAuth 2.1, delegation, audit.
Public registries, trust scoring, signed receipts, and verifiable attestation.
- agentattest - Verifiable provenance for AI coding agents. Binds agent runs, diffs, PRs, artifacts, and approvals into attestations.
- AgentGuard - Security guard for AI agents. Blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules.
- agentregistry - Centralized, curated registry for AI agent skills.
- ai-trust - Package scanner that reports a 0–100 trust score through
ai-trust check <pkg>. - Attestix - Attestation infrastructure for AI agents. DID-based agent identity, W3C Verifiable Credentials, EU AI Act compliance.
- attestplane - Verifiable audit substrate designed to support AI-agent record-keeping requirements.
- bootproof - Zero-trust supervisor that boots any repository or agent artifact to a verifiable, known-good state.
- halo-record - Tamper-evident runtime records for AI agents. Hash-chained, dependency-free, verifiable by anyone.
- hvtracker - AI Agent Trust Registry. Independent, evidence-based trust scores for 172+ open-source AI agents.
- kairon-protocol - Attestation protocol for AI coding agents. Turns completed tasks into verifiable receipts.
- logpose - Verifiable reputation + attestation SDK for AI agents.
- mimir - Verifiable provenance for MCP tool-call results. Signed envelopes + quality scoring.
- Open Agent Trust Registry - Open root-of-trust for agent identity. Public, federated registry of trusted attestation issuers.
- provetrail - Open standard for verifiable execution provenance. Portable, third-party-verifiable records.
- ToolTrust Directory - Trust layer for AI agents. Curated registry of secure tools and MCP servers with A-F risk grading.
- treeship - Portable trust receipts for agent workflows. Signed, chained, verifiable.
- Verifiable ClawGuard - Use TEE attestation to prove an agent is running behind known guardrails.
Credit-score-style reputation systems and trust scoring for agents.
- AgenticTrust - Decentralized reputation, scoring, and discovery infrastructure for AI agents.
- djd-agent-score - Reputation scoring for AI agent wallets on Base.
- mnemopay-sdk - Trust & reputation layer for AI agents. Agent Credit Score (300-850) + Merkle-anchored ledger.
- nobulex - Trust economy for autonomous AI agents. Credit scores for machines. Agents earn Trust Capital through verified behavior.
- repute - Open-source reputation scoring for AI agents using Ethereum Attestation Service and Base.
Immutable audit logs, hash-chained event records, session replay, and observability infrastructure.
- agent-witness - Session recorder and audit log for AI coding agents. Replay Claude Code sessions as TUI timeline.
- agentlens - Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging.
- clawlens - Agent observability and guardrails for OpenClaw. Risk scoring, audit trails, dashboard.
- DecisionNotary - Decentralized decision-notary bridging AI observability with on-chain identity.
- deconvolute - Policy-as-code enforcement and observability for MCP tool calls. Cryptographic integrity chains.
- forgesight - Vendor-neutral, OpenTelemetry-first telemetry for AI agents. Traces, cost, budgets, audit trails.
- notmemory - Tamper-proof agent memory with audit trails, rollback, GDPR tombstoning, and semantic search.
- soma - Local-first AI agent governance with verifiable, tamper-evident audit trails.
- SoulGuard - Open trust layer for AI-agent memory. Tamper-evident memory and cryptographic agent identity.
- trailing - Immutable audit trails for AI agents. Compliance-ready logging for Claude Code, Codex, Cursor, CrewAI.
- trishula-agent-telemetry - Deterministic agent observability. Merkle-chained audit trails. Anomaly detection. Zero dependencies.
- vaara - Open-source evidence layer for AI governance. Gates every agent tool call against your policies with verifiable receipts.
Security toolkits, vulnerability scanning, skill vetting, and supply chain security.
- agent-bom - AI supply-chain and cloud security scanner. Self-hosted control plane for agents, MCP, and packages.
- agentseal - Security toolkit for AI agents. Scan for dangerous skills and MCP configs, monitor supply chain attacks.
- AI-Infra-Guard - Full-stack AI Red Teaming platform. Agent Security Scan, supply chain verification, and prompt security for AI ecosystems.
- awesome-skills-security - Security testing toolkit for AI agents. Curated SecLists wordlists, injection payloads, and expert agents for authorized security testing.
- ClawGuard - Comprehensive security toolkit for autonomous agents (OpenClaw, Claude Code, Cursor).
- clawguard (yourclaw) - Security scanning and trust registry for AI agent skills (Clawdbot, MoltBot, OpenClaw, ClawHub).
- hackagent - Open-source security toolkit to detect vulnerabilities in your AI agents.
- hackmyagent - Security testing toolkit for scanning AI agents and MCP servers and exercising known attack techniques.
- MindJack - Security toolkit that extracts agent memories and rewrites instructions. Red-teaming tool.
- ops0 CLI - Cloud infrastructure-plan scanner and governance CLI for agent-generated infrastructure as code.
- SecOpsAgentKit - Security operations toolkit for AI coding agents. 25+ skills for vulnerability detection, container scanning.
- skillfortify - Security scanner for AI agent skills and plugins. Static analysis, supply chain vulnerability detection.
Curated registries, security-audited marketplaces, and vetted skill catalogs for AI agents.
- Agent Skill Exchange - Curated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP.
- AI Skill Store - Marketplace of security-reviewed skills for Claude, Codex, and Claude Code.
- Awesome Claude (HeyClaude) - Curated registry and distribution surface for Claude and AI-workflow assets: agents, skills, MCP servers.
- awesome-agent-skills - Curated, auto-updated awesome-list of vetted AI agent skills with quality ratings.
- Binance Skills Hub - Open skills marketplace giving AI agents native access to crypto exchange capabilities through curated, verified skills.
- Claude Code Plugins Plus - Open-source marketplace. 425 plugins, 2,810 skills, 200 agents for Claude Code.
- Claude Code Skills - Marketplace of Claude Code skills for development workflows.
- Mercury Agent Skills - Curated registry of reusable agent skills for Mercury Agent, OpenClaw, and Hermes Agent.
- n-skills - Curated plugin marketplace for AI agents, compatible with Claude Code, Codex, and OpenClaw.
- PM Skills - Marketplace for agentic skills, commands, and plugins focused on project management and development workflows.
- Trail of Bits Curated Skills - Curated, community-vetted Claude Code plugin marketplace from the respected security firm.
- x-cmd/skill - Human-vetted, community-curated skills for AI coding and agent tools.
Open standards and specifications, including work hosted by foundations and community-led efforts. Inclusion does not imply endorsement or foundation affiliation unless the entry explicitly says so.
- AAIF Agent Card MCP - Linux Foundation AAIF Agent Card MCP. Publish
/.well-known/agent-card, bridge A2A and OASF. - Agentic AI Foundation - Community repository tracking the Agentic AI Foundation ecosystem.
- CapiscIO RFCs - Request for Comments for CapiscIO protocols and standards. AGCP, trust policies, agent identity.
- OASF Agent Directory MCP - Cisco AGNTCY bridge under Linux Foundation for the OASF Agent Directory.
Protocols for inter-agent communication, trust networks, and agent economies.
- A2A .NET - .NET implementation of the A2A protocol for secure, interoperable agent communication.
- A2A Go - Go implementation of the A2A protocol for agent interoperability.
- A2A Rust - Type-safe, async Rust SDK for the Agent2Agent (A2A) protocol.
- Agent Identity Protocol (AIP) draft - Concept draft of AIP. Governance layer for autonomous agents covering identity, permissions, audit.
- Agent2Agent (A2A) - Google's open protocol enabling communication and interoperability between agentic applications. 24,600+★.
- Agentic Commerce Protocol (ACP) - Open standard for connecting AI agents with commerce infrastructure — payments, orders, and product discovery.
- AINRP - AI Identity and Non-Repudiation Protocol for trusted autonomous agents. Smart contracts, architecture, tokenomics.
- ClawNet - Governed multi-agent social network. Every AI agent acts under human-granted identity and scoped authorization.
- dos-kernel - Catch AI agents when they lie about what they shipped. Verifies claims against git.
- EEP - Open standard for push-based, verifiable communication between digital entities and agents.
- Fides Protocol - Trust layer for AI agents. Every tool call is intercepted, verified, and authorized.
- Graphenium - Trust and verification layer for AI-generated code changes.
- HITL Protocol - Human-in-the-Loop Protocol for autonomous agent services. Open standard (v0.8).
- Kinetic Trust Protocol - Dynamic, physics-based authorization of autonomous agents.
- MoveGate Protocol - Agent Identity, Authorization, and Trust Infrastructure for Sui. On-chain mandate delegation.
- neus/network - Open trust network for apps, people, and AI agents.
- Oath Protocol - Protocol for cryptographically verifiable human intent. Agent authorization, local-first, offline-capable.
- Python A2A - Python library for implementing Google's Agent-to-Agent (A2A) protocol.
- sati - Trust infrastructure for million-agent economies on Solana. Identity, reputation, validation.
- swarm-hedera - Agent identity, HCS messaging, staking, governance, NFTs, trust verification on Hedera.
TEE-backed attestation, confidential computing, and hardware-enforced security.
- Confidential AI - Confidential computing stack for AI workloads. Run inference, training, agents in hardware-encrypted environments.
- Confidential Computing Expert Skill - AI agent skill for confidential computing. TEE platforms, attestation protocols, KRAB verifiability.
- QWED Verification - Deterministic verification layer for AI systems. Verifies outputs using mathematics and symbolic reasoning.
- TEE-backed Private Memory - Private memory layer using Gramine SGX/RA-TLS for AI agents.
- Awesome A2A Agents - Curated list of tools, frameworks, and projects built on the Agent-to-Agent (A2A) protocol.
- Awesome AI Agent Protocols - Protocols, tools, and services for the AI agent infrastructure stack.
- Awesome AI Agents Security - Tools and resources for securing autonomous agents, including runtime protection, red-teaming, sandboxing, guardrails, and agent identity.
- Awesome Machine Economy - The machine economy ecosystem — agent payments, commerce, and finance.
See contributing.md for submission guidelines, format requirements, and CI checks that run on every pull request.
See CRITERIA.md for the full inclusion criteria — relevance domains, quality gates (star threshold, activity, description), categorization rules, and exclusion policies. Validation CI blocks missing, archived, or unverifiable repositories and reports other quality signals for human review.
To the extent possible under law, the curator has waived all copyright and related or neighboring rights to this work.